4 papers
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha +2
Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes thr…
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Susmit Agrawal, Krishn Vishwas Kher, Saksham Mittal +2
Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowl…
Unsupervised Structural-Counterfactual Generation under Domain Shift
Krishn Vishwas Kher, Lokesh Venkata Siva Maruthi Badisa, Saksham Mittal +3
Motivated by the burgeoning interest in cross-domain learning, we present a novel generative modeling challenge: generating counterfactual samples in a target domain based on factu…
Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models
Krishn Vishwas Kher, Saksham Mittal, Aditya Varun +2
One of the main concerns while deploying machine learning models in real-world applications is fairness. Counterfactual fairness has emerged as an intuitive and natural definition…